© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5191
    Prev
    Next
    INDEX
    Explanations

    URL placeholders in contact info

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perturb
    1.39
     (
    1.32
     dorm
    1.29
     tocar
    1.27
     ferr
    1.27
     apart
    1.25
     mort
    1.21
     choc
    1.20
     terap
    1.19
     tog
    1.17
    POSITIVE LOGITS
    ؟
    1.52
    Anchor
    1.50
    indungan
    1.49
    নু
    1.49
    Ϳ
    1.41
    હેરા
    1.40
    بو
    1.40
    ൻ
    1.40
    账户
    1.39
     جديد
    1.38
    Activations Density 0.025%

    No Known Activations